turboderp-org/exllamav2
1
0
Fork 0
mirror of https://github.com/turboderp-org/exllamav2.git synced 2026-04-27 09:44:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,459 Commits 3 Branches 43 Tags
master
Commit Graph

1459 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
MikeRoz47
61450b4860 concatenate the sin and cos tensors (#758) 2025-04-11 22:11:13 +02:00
turboderp
b148bb42b8 Fix Gemma3 head norm (RMS) 2025-04-11 00:18:06 +02:00
turboderp
d471d44f01 Gemma3 local RoPE fixes 2025-04-10 22:16:08 +02:00
turboderp
a03db457ef Fix: Prioritize default head_dim when provided by architecture (Gemma3) over computed head_dim 2025-03-15 11:52:51 +01:00
turboderp
385a5162ba Fix: Correctly read query_pre_attn_scalar from text_config (Gemma3) 2025-03-15 11:01:33 +01:00
turboderp
17762c177f Merge remote-tracking branch 'origin/dev' into dev 2025-03-15 01:37:43 +01:00
turboderp
6f7623ff0e Update examples 2025-03-15 01:30:52 +01:00
turboderp
77a1e2cb0c Warn instead of failing for unsupported vision model 2025-03-15 00:13:52 +01:00
turboderp
578fd4234f Support Gemma3 (vision) 2025-03-15 00:13:19 +01:00
turboderp
c0267e37fe Support Gemma3 (text) 2025-03-15 00:06:56 +01:00
turboderp
565339101b Allow text model to use Q/K norm while vision model doesn't 2025-03-15 00:06:56 +01:00
turboderp
07afc90788 Tensor renaming kludge (Gemma3 has one _weight tensor) 2025-03-15 00:06:56 +01:00
turboderp
e2fa480595 Auto expand Q/K norm weight to match number of heads 2025-03-15 00:06:56 +01:00
turboderp
a88c18cac1 Add architecture-specific config defaults (Gemma3 config.json is incomplete) 2025-03-15 00:06:56 +01:00
turboderp
b6c1912f29 Respect norm_constant_bias in Q/K norms (Gemma3) 2025-03-15 00:06:56 +01:00
turboderp
4b5dbecdc1 Allow key prefix for lm_head (Gemma3) 2025-03-15 00:06:56 +01:00
turboderp
4844f3873c Upcast MM embeddings when residual is FP32 2025-03-15 00:06:56 +01:00
turboderp
fe51a8f4b5 Correctly include Q/K norms when compiling model 2025-03-15 00:06:56 +01:00
turboderp
38f4d7c87d Allow loading transposed unquantized linear layer 2025-03-15 00:06:56 +01:00
turboderp
9669fa33c9 Allow component models to use learned pos embeddings without regarding LLM max_seq_len 2025-03-15 00:06:56 +01:00
turboderp
7b05acd233 Allow per-layer RoPE theta 2025-03-15 00:06:56 +01:00
turboderp
23395dfa42 Fix FP32 residual for paged attn 2025-03-14 23:09:31 +01:00
Thomas
eaf8ad1041 Update chat.py, include multi-line input support and context clearing through input (#738) 
* Update chat.py, include multi-line input support and context clearing

- Enable multi-line input (mli) support through the -mli argument. When using mli, end input with the EOF char (return/Ctrl+D on Unix, return/Ctrl+Z/return on Windows)
- Allow context clearing outside of amnesia by inputting "clear"

* Adding qwq chat mode, adding the ability to forget thinking context
 2025-03-10 15:28:33 +01:00
turboderp
d8fa1a8250 Support partial_rotary_factor (Phi-4 mini) 2025-02-28 08:51:11 +01:00
turboderp
2e630aefdd Fix alt pos embeddings and block diagonal mask when flash-attn is disabled 2025-02-13 22:13:48 +01:00
turboderp
1a80d38891 Update build actions 2025-02-08 03:29:05 +01:00
turboderp
f1c4126045 Update build actions 2025-02-08 03:14:32 +01:00
turboderp
f98a7b7099 Update build actions 2025-02-08 03:08:45 +01:00
turboderp
096076b3fd Update build actions 2025-02-08 02:49:21 +01:00
turboderp
0f4a9f0042 Update build actions 2025-02-08 01:36:51 +01:00
turboderp
f3de3cbd34 Update build actions 2025-02-08 01:05:22 +01:00
turboderp
94e57904bc Update build actions v0.2.8 2025-02-08 00:57:29 +01:00
turboderp
3a9618d471 Update build actions 2025-02-08 00:44:44 +01:00
turboderp
3486f9eb71 Merge branch 'refs/heads/dev' 2025-02-08 00:26:52 +01:00
turboderp
6e4a84a1e3 Bump to 0.2.8 2025-02-08 00:26:30 +01:00
turboderp
d05fbcc854 Fix Pixtral regression 2025-02-04 21:01:23 +01:00
turboderp
96b2f9df77 Add Qwen2.5 mode to grounding demo 2025-01-29 22:41:36 +01:00
turboderp
cce6f95cd3 Initial support for Qwen2.5-VL 2025-01-29 03:03:36 +01:00
turboderp
d0413b06f8 Check length of gpu_split in model_init 2025-01-09 11:36:25 +01:00
turboderp
c8fa853c89 Test script: Allow --eval_rows in wiki2 ppl test 2025-01-09 11:14:48 +01:00
turboderp
318435db81 Sampler: Remove superfluous pre-sort pass 2025-01-09 11:14:19 +01:00
turboderp
d302fa3d37 Optimizer: Ensure weight budget is fully used up 2025-01-09 11:14:03 +01:00
turboderp
b400394f06 Update build actions 2025-01-09 11:13:03 +01:00
turboderp
b9c025b4b1 Enable large runner 2024-12-30 05:47:11 +01:00
turboderp
c41acd5c11 Extra ROCm 6.2 actions 2024-12-30 04:31:44 +01:00
turboderp
7c08c6df71 Deactivate mamba 2024-12-30 04:07:50 +01:00
turboderp
c8075cabf4 Update conda-incubator 2024-12-30 04:00:15 +01:00
turboderp
ae241a9af5 Fix video example v0.2.7 2024-12-30 02:24:49 +01:00
turboderp
1ef618389b Bump to v0.2.7 2024-12-30 02:19:19 +01:00
turboderp
b010cb950f Fix compilation errors on aarch64 2024-12-29 20:30:59 +01:00